Facilitating personalized vehicle occupant comfort

Abstract

A vehicle occupant comfort system, comprises a processor that stores computer executable components stored in memory. A plurality of sensors sense ambient conditions associated with exterior and interior conditions of a vehicle. A context component infers or determines context of an occupant of the vehicle. A comfort model component implicitly and explicitly trained on occupant comfort related data analyzes information from the plurality of sensors and context component. A comfort controller adjusts environmental conditions of a passenger compartment of the vehicle based at least in part on output of the comfort model component.

What is claimed is: 
     
       1. A system comprising:
 a memory storing one or more computer readable and executable instructions; and 
 a processor operably coupled to the memory and that executes the computer readable and executable instructions, causing the processor to:
 train a comfort model corresponding to an occupant of a vehicle, by applying a machine learning approach to training samples, wherein a training sample includes:
 prior ambient conditions associated with the vehicle and prior body parameters associated with the occupant; 
 a pre-adjustment status and a post-adjustment status of comfort facilities of the vehicle, corresponding to the prior ambient conditions and the prior body parameters; and 
 a prior continuous comfort index based on a Euclidean distance between the pre-adjustment and post-adjustment statuses; 
 
 sense, via a plurality of sensors, current ambient conditions associated with the vehicle and current body parameters associated with the occupant; 
 determine a context of the occupant; 
 infer, by the comfort model, a current continuous comfort index indicating a current comfort level of the occupant, based on the current ambient conditions, the current body parameters, and the context; 
 determine one or more of the current ambient conditions to be adjusted to improve the current comfort level of the occupant, by:
 clustering, according to prior body parameters, the training samples that have a prior continuous comfort index better than the current continuous comfort index; 
 identifying a cluster having prior body parameters closest to the current body parameters; 
 calculating representative ambient conditions based on the prior ambient conditions of the identified cluster; and 
 identifying, as the determined one or more of the current ambient conditions, one or more of the current ambient conditions that are worse, by a predetermined benchmark, than the representative ambient conditions; and 
 
 adjust environmental conditions of a passenger compartment of the vehicle based on the determined one or more of the current ambient conditions. 
 
 
     
     
       2. The system of  claim 1 , wherein the plurality of sensors further sense information selected from the group consisting of body temperature of the occupant and an amount of clothing worn by the occupant. 
     
     
       3. The system of  claim 1 , wherein the context includes information selected from the group consisting of an action of the occupant, a destination for the occupant, and a trip length for the occupant. 
     
     
       4. The system of  claim 1 , wherein the comfort model determines an environmental condition for at least one of one or more occupants of the vehicle. 
     
     
       5. The system of  claim 1 , wherein the processor determines one or more comfort profiles for high frequency occupants of the vehicle. 
     
     
       6. The system of  claim 1 , wherein the processor identifies, via facial recognition, the occupant of the vehicle. 
     
     
       7. The system of  claim 6 , wherein the processor infers, via pattern recognition, occupant comfort from one or more facial expressions. 
     
     
       8. A system comprising:
 a processor that executes computer-executable instructions stored on a computer-readable memory, wherein the computer-executable instructions cause the processor to:
 train a comfort model corresponding to an occupant of a vehicle, by applying a machine learning approach to training samples, wherein a training sample includes:
 prior ambient conditions associated with the vehicle and prior body parameters associated with the occupant; 
 a pre-adjustment status and a post-adjustment status of comfort facilities of the vehicle, corresponding to the prior ambient conditions and the prior body parameters; and 
 a prior continuous comfort index based on a Euclidean distance between the pre-adjustment and post-adjustment statuses; 
 
 sense, via one or more sensors, current ambient conditions associated with the vehicle and current body parameters associated with the occupant; 
 infer, by the comfort model, a current continuous comfort index indicating a current comfort level of the occupant, based on the current ambient conditions and the current body parameters; 
 determine one or more of the current ambient conditions to be adjusted to improve the current comfort level of the occupant, by:
 clustering, according to prior body parameters, the training samples that have a prior continuous comfort index better than the current continuous comfort index; 
 identifying a cluster having prior body parameters closest to the current body parameters; 
 calculating representative ambient conditions based on the prior ambient conditions of the identified cluster; and 
 identifying, as the determined one or more of the current ambient conditions, one or more of the current ambient conditions that are worse, by a predetermined benchmark, than the representative ambient conditions; and 
 
 adjust one or more of the comfort facilities of the vehicle corresponding to the determined one or more of the current ambient conditions. 
 
 
     
     
       9. The system of  claim 8 , wherein the machine learning approach is a regression analysis. 
     
     
       10. The system of  claim 8 , wherein the current and prior ambient conditions include at least:
 air temperature inside the vehicle; 
 noise volume inside the vehicle; and 
 light intensity inside the vehicle. 
 
     
     
       11. The system of  claim 10 , wherein the current and prior ambient conditions further include at least one from the group consisting of:
 humidity inside the vehicle; 
 air quality inside the vehicle; and 
 pressure inside the vehicle. 
 
     
     
       12. The system of  claim 8 , wherein the current and prior body parameters include:
 heart rate of the occupant; and 
 skin temperature of the occupant. 
 
     
     
       13. The system of  claim 12 , wherein the current and prior body parameters further include:
 respiratory rate of the occupant; 
 skin humidity of the occupant; and 
 blood oxygen saturation of the occupant. 
 
     
     
       14. The system of  claim 8 , wherein the computer-executable instructions further cause the processor to infer a context of the occupant, including at least a recent activity of the occupant, and wherein the current continuous comfort index is based in part on the context. 
     
     
       15. An apparatus comprising:
 a processor that executes computer-executable instructions stored on a computer-readable memory, wherein the computer-executable instructions cause the processor to:
 train a comfort model corresponding to an occupant of a vehicle, by applying a machine learning approach to training samples, wherein a training sample includes:
 past interior conditions associated with the vehicle and past biometric data associated with the occupant; and 
 a past continuous comfort index corresponding to the past interior conditions and the past biometric data, based on manual adjustments by the occupant to comfort facilities of the vehicle in response to the past interior conditions and the past biometric data; 
 
 sense, via one or more sensors, current interior conditions associated with the vehicle and current biometric data associated with the occupant; 
 infer, by the comfort model, a current continuous comfort index indicating a current comfort level of the occupant, based on the current interior conditions and the current biometric data; 
 determine one or more of the current interior conditions to be adjusted to improve the current comfort level of the occupant, by:
 identifying a cluster of training samples having a past continuous comfort index better than the current continuous comfort index and having past biometric data closest to the current biometric data; and 
 identifying, as the determined one or more of the current interior conditions, one or more of the current interior conditions that are worse, by a predetermined benchmark, than representative interior conditions of the identified cluster; and 
 
 adjust one or more of the comfort facilities of the vehicle corresponding to the determined one or more of the current interior conditions. 
 
 
     
     
       16. The apparatus of  claim 15 , wherein the current and past interior conditions include at least:
 air temperature inside the vehicle; 
 noise volume inside the vehicle; and 
 light intensity inside the vehicle. 
 
     
     
       17. The apparatus of  claim 16 , wherein the current and past interior conditions further include at least one from the group consisting of:
 humidity inside the vehicle; 
 air quality inside the vehicle; and 
 pressure inside the vehicle. 
 
     
     
       18. The apparatus of  claim 15 , wherein the current and past biometric data include:
 heart rate of the occupant; and 
 skin temperature of the occupant. 
 
     
     
       19. The apparatus of  claim 18 , wherein the current and past biometric data further include:
 respiratory rate of the occupant; 
 skin humidity of the occupant; and 
 blood oxygen saturation of the occupant. 
 
     
     
       20. The apparatus of  claim 15 , wherein the computer-executable instructions further cause the processor to infer a context of the occupant, including at least a recent activity of the occupant, and wherein the current continuous comfort index is based in part on the context.